© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 20902
    Prev
    Next
    INDEX
    Explanations

    state names or words starting with 'st'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Оно
    0.47
     it
    0.45
    ަރ
    0.41
     interrogation
    0.40
     paramagnetic
    0.40
     Phật
    0.39
     Анто
    0.39
    ،
    0.39
     enquiry
    0.39
     rupture
    0.38
    POSITIVE LOGITS
     ஸ்ட
    0.47
    ரே
    0.43
     સ્ટ
    0.42
     സ്റ്റ
    0.41
     Staaten
    0.39
    ستون
    0.39
    на
    0.39
     st
    0.38
    дово
    0.38
     States
    0.38
    Activations Density 0.134%

    No Known Activations